© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45345
    Prev
    Next
    INDEX
    Explanations

    special characters and names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ounded
    -0.07
    ecided
    -0.06
    elly
    -0.06
    orit
    -0.06
    na
    -0.06
    elit
    -0.06
    uffer
    -0.06
     Faculty
    -0.06
    ä¸Ģéģĵ
    -0.06
    ed
    -0.06
    POSITIVE LOGITS
    éĽĩçĶ¨
    0.08
    rens
    0.08
    :mm
    0.07
    èĶ·
    0.07
    è´Łè´£ä»»
    0.07
    ustin
    0.07
     Suomi
    0.07
    _mtx
    0.07
     Bing
    0.07
    [NUM
    0.07
    Activations Density 0.025%

    No Known Activations